INDEX
Explanations
temporal references and specific dates in a context related to events
New Auto-Interp
Head Attr Weights
0:0.01
1:0.12
2:0.16
3:0.05
4:0.01
5:0.03
6:0.08
7:0.07
8:0.07
9:0.20
10:0.08
11:0.07
Negative Logits
cause
-1.19
affirmative
-1.00
Frazier
-0.99
Racial
-0.97
earchers
-0.95
supremacist
-0.91
CoC
-0.90
luster
-0.90
pts
-0.89
Subject
-0.88
POSITIVE LOGITS
amph
1.16
gencies
1.12
thereof
1.12
kj
1.09
Reloaded
1.09
icion
1.08
vine
1.06
htt
1.02
Nin
1.01
thereafter
1.00
Activations Density 0.254%